{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.778021978021978,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.068535327911377,
      "learning_rate": 0.0,
      "loss": 1.0606,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.268423318862915,
      "learning_rate": 9.56e-05,
      "loss": 1.1983,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.045927882194519,
      "learning_rate": 0.0001912,
      "loss": 1.0628,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.028908371925354,
      "learning_rate": 0.0002868,
      "loss": 0.9173,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6483846306800842,
      "learning_rate": 0.0003824,
      "loss": 0.7759,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.7689517736434937,
      "learning_rate": 0.000478,
      "loss": 0.9309,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5526404976844788,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.96,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.4260517656803131,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8695,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.34387385845184326,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8246,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.33756059408187866,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.805,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.5314936637878418,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8365,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5229127407073975,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.838,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.48703446984291077,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.773,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.524895966053009,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7794,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5241197347640991,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7233,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.427020788192749,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7957,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5390051603317261,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.8339,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.31555530428886414,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7379,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3968167304992676,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.6715,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.37160152196884155,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7653,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40373656153678894,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7728,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.360177218914032,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7641,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5294693112373352,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7356,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.353331595659256,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7071,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.49404677748680115,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.7861,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3531878590583801,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7469,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4992196261882782,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7605,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.39656317234039307,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.772,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.41846686601638794,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.7356,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.4010296165943146,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7164,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.39482295513153076,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.7471,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.4151882231235504,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.6996,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.36281782388687134,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.6891,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.34789708256721497,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.7758,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.324373722076416,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7226,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.42178890109062195,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7202,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.308438241481781,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.6874,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3963092267513275,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7376,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.44302892684936523,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.7081,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3021492063999176,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.6247,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.43004491925239563,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7669,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3463588058948517,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.7017,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.34282755851745605,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.689,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3126462996006012,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6595,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.4455788731575012,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.7789,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.43091949820518494,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.6629,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3956051170825958,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.7038,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.34474050998687744,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.6247,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34399884939193726,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.7179,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.40537482500076294,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7844,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.2834356427192688,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.7072,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4583128094673157,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.6838,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.368510901927948,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.7243,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3794223964214325,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.6682,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3720533847808838,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.7399,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.26934292912483215,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.7528,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2473444938659668,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7546,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.29776763916015625,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.7134,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.30960676074028015,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.6635,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.29519444704055786,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.7917,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.30791789293289185,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.747,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3696693778038025,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.654,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3656329810619354,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7181,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.33191412687301636,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.7213,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.37534675002098083,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.6989,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.31701603531837463,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.7248,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.33182188868522644,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.693,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.37241753935813904,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.7017,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2879069745540619,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7336,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3153330981731415,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.6674,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.28542593121528625,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.6966,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.35462895035743713,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.662,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3499428927898407,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.616,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3505977392196655,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.6786,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.45479053258895874,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.6899,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3608059287071228,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.773,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.29298636317253113,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.7471,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3075357973575592,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.6878,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.33668023347854614,
      "learning_rate": 0.000400629711751663,
      "loss": 0.6526,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.38277485966682434,
      "learning_rate": 0.000399569844789357,
      "loss": 0.6973,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.31462499499320984,
      "learning_rate": 0.000398509977827051,
      "loss": 0.6926,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.39728376269340515,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7752,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4079730212688446,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7529,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2829400897026062,
      "learning_rate": 0.000395330376940133,
      "loss": 0.6805,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.28787168860435486,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.6955,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3676906228065491,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.7451,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.30598631501197815,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.6962,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2758977711200714,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.6525,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.2694230079650879,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.6458,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.35207247734069824,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.7354,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4389498829841614,
      "learning_rate": 0.00038791130820399114,
      "loss": 0.7062,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.31410330533981323,
      "learning_rate": 0.0003868514412416852,
      "loss": 0.6619,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.34998422861099243,
      "learning_rate": 0.00038579157427937917,
      "loss": 0.7097,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3565973937511444,
      "learning_rate": 0.0003847317073170732,
      "loss": 0.7555,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3209623694419861,
      "learning_rate": 0.0003836718403547672,
      "loss": 0.712,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2885645627975464,
      "learning_rate": 0.0003826119733924612,
      "loss": 0.696,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3163300156593323,
      "learning_rate": 0.0003815521064301552,
      "loss": 0.7392,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2682330310344696,
      "learning_rate": 0.00038049223946784927,
      "loss": 0.6998,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2647293210029602,
      "learning_rate": 0.00037943237250554325,
      "loss": 0.7224,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.28071725368499756,
      "learning_rate": 0.0003783725055432373,
      "loss": 0.6809,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3356964588165283,
      "learning_rate": 0.0003773126385809313,
      "loss": 0.6463,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3239942491054535,
      "learning_rate": 0.00037625277161862527,
      "loss": 0.7375,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3177068829536438,
      "learning_rate": 0.0003751929046563193,
      "loss": 0.7826,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.32427293062210083,
      "learning_rate": 0.00037413303769401335,
      "loss": 0.7377,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3223443627357483,
      "learning_rate": 0.00037307317073170733,
      "loss": 0.7475,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.27960214018821716,
      "learning_rate": 0.0003720133037694014,
      "loss": 0.6721,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3128959536552429,
      "learning_rate": 0.00037095343680709536,
      "loss": 0.7188,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.26712024211883545,
      "learning_rate": 0.00036989356984478935,
      "loss": 0.7103,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.2812448740005493,
      "learning_rate": 0.0003688337028824834,
      "loss": 0.6957,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3096236288547516,
      "learning_rate": 0.0003677738359201774,
      "loss": 0.729,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3115459084510803,
      "learning_rate": 0.0003667139689578714,
      "loss": 0.7084,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.2779158651828766,
      "learning_rate": 0.00036565410199556546,
      "loss": 0.7266,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.308214008808136,
      "learning_rate": 0.0003645942350332594,
      "loss": 0.6667,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.3447636365890503,
      "learning_rate": 0.00036353436807095343,
      "loss": 0.669,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3795604705810547,
      "learning_rate": 0.00036247450110864747,
      "loss": 0.7255,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3086259663105011,
      "learning_rate": 0.00036141463414634146,
      "loss": 0.7072,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3496393859386444,
      "learning_rate": 0.0003603547671840355,
      "loss": 0.6444,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3314879536628723,
      "learning_rate": 0.00035929490022172954,
      "loss": 0.6618,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.298123300075531,
      "learning_rate": 0.00035823503325942347,
      "loss": 0.6552,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.341611385345459,
      "learning_rate": 0.0003571751662971175,
      "loss": 0.6777,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.2922254800796509,
      "learning_rate": 0.00035611529933481155,
      "loss": 0.687,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.33807608485221863,
      "learning_rate": 0.00035505543237250554,
      "loss": 0.7163,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.33568352460861206,
      "learning_rate": 0.0003539955654101996,
      "loss": 0.6678,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.3700680136680603,
      "learning_rate": 0.0003529356984478936,
      "loss": 0.762,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.33432433009147644,
      "learning_rate": 0.00035187583148558755,
      "loss": 0.7006,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3129095733165741,
      "learning_rate": 0.0003508159645232816,
      "loss": 0.7381,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.31153926253318787,
      "learning_rate": 0.00034975609756097563,
      "loss": 0.778,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3667391538619995,
      "learning_rate": 0.0003486962305986696,
      "loss": 0.6813,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3075600266456604,
      "learning_rate": 0.00034763636363636366,
      "loss": 0.6748,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3221612572669983,
      "learning_rate": 0.0003465764966740577,
      "loss": 0.6337,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.31721261143684387,
      "learning_rate": 0.00034551662971175163,
      "loss": 0.7968,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.33169451355934143,
      "learning_rate": 0.00034445676274944567,
      "loss": 0.7365,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.33635473251342773,
      "learning_rate": 0.0003433968957871397,
      "loss": 0.6597,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3257780969142914,
      "learning_rate": 0.0003423370288248337,
      "loss": 0.6981,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.469706654548645,
      "learning_rate": 0.00034127716186252774,
      "loss": 0.6684,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3314266800880432,
      "learning_rate": 0.0003402172949002218,
      "loss": 0.6754,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.4370989501476288,
      "learning_rate": 0.00033915742793791577,
      "loss": 0.7134,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.36346378922462463,
      "learning_rate": 0.00033809756097560975,
      "loss": 0.7277,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.2834616005420685,
      "learning_rate": 0.0003370376940133038,
      "loss": 0.7331,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.3309989273548126,
      "learning_rate": 0.0003359778270509978,
      "loss": 0.6404,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3594907522201538,
      "learning_rate": 0.0003349179600886918,
      "loss": 0.6605,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3308711051940918,
      "learning_rate": 0.00033385809312638586,
      "loss": 0.6817,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.2964507043361664,
      "learning_rate": 0.00033279822616407985,
      "loss": 0.7109,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.29236412048339844,
      "learning_rate": 0.00033173835920177384,
      "loss": 0.6977,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3020668923854828,
      "learning_rate": 0.0003306784922394679,
      "loss": 0.6785,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.2710575461387634,
      "learning_rate": 0.00032961862527716186,
      "loss": 0.6656,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.287383109331131,
      "learning_rate": 0.0003285587583148559,
      "loss": 0.758,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.30787622928619385,
      "learning_rate": 0.00032749889135254994,
      "loss": 0.6859,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3401782810688019,
      "learning_rate": 0.00032643902439024393,
      "loss": 0.7403,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.3512507677078247,
      "learning_rate": 0.0003253791574279379,
      "loss": 0.7589,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.31852632761001587,
      "learning_rate": 0.0003243192904656319,
      "loss": 0.6651,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4142078161239624,
      "learning_rate": 0.00032325942350332594,
      "loss": 0.581,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3398224711418152,
      "learning_rate": 0.00032219955654102,
      "loss": 0.6633,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.36505943536758423,
      "learning_rate": 0.00032113968957871397,
      "loss": 0.6708,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3728950619697571,
      "learning_rate": 0.000320079822616408,
      "loss": 0.6397,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.35360872745513916,
      "learning_rate": 0.000319019955654102,
      "loss": 0.6511,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.378539502620697,
      "learning_rate": 0.000317960088691796,
      "loss": 0.6677,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.32942622900009155,
      "learning_rate": 0.00031690022172949,
      "loss": 0.7396,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.3780038356781006,
      "learning_rate": 0.00031584035476718407,
      "loss": 0.6692,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3802650570869446,
      "learning_rate": 0.00031478048780487805,
      "loss": 0.6256,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.31385597586631775,
      "learning_rate": 0.0003137206208425721,
      "loss": 0.6192,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.28268927335739136,
      "learning_rate": 0.0003126607538802661,
      "loss": 0.5998,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.3524104356765747,
      "learning_rate": 0.00031160088691796007,
      "loss": 0.6909,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.358532577753067,
      "learning_rate": 0.0003105410199556541,
      "loss": 0.6954,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3227754533290863,
      "learning_rate": 0.00030948115299334815,
      "loss": 0.621,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3722781240940094,
      "learning_rate": 0.00030842128603104213,
      "loss": 0.6397,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.33485153317451477,
      "learning_rate": 0.0003073614190687362,
      "loss": 0.5658,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.34761011600494385,
      "learning_rate": 0.00030630155210643016,
      "loss": 0.7183,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.32561367750167847,
      "learning_rate": 0.00030524168514412415,
      "loss": 0.6109,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.36919522285461426,
      "learning_rate": 0.0003041818181818182,
      "loss": 0.6526,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.37742218375205994,
      "learning_rate": 0.00030312195121951223,
      "loss": 0.5494,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.35670945048332214,
      "learning_rate": 0.0003020620842572062,
      "loss": 0.557,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3793083131313324,
      "learning_rate": 0.00030100221729490026,
      "loss": 0.6312,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.2898044288158417,
      "learning_rate": 0.00029994235033259424,
      "loss": 0.6251,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.34872108697891235,
      "learning_rate": 0.00029888248337028823,
      "loss": 0.6453,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3174109160900116,
      "learning_rate": 0.00029782261640798227,
      "loss": 0.5793,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.31417199969291687,
      "learning_rate": 0.0002967627494456763,
      "loss": 0.5836,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.3724935054779053,
      "learning_rate": 0.0002957028824833703,
      "loss": 0.6775,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3207768499851227,
      "learning_rate": 0.00029464301552106434,
      "loss": 0.6249,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.34812575578689575,
      "learning_rate": 0.0002935831485587583,
      "loss": 0.6363,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.4467976987361908,
      "learning_rate": 0.0002925232815964523,
      "loss": 0.6074,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.4021419584751129,
      "learning_rate": 0.00029146341463414635,
      "loss": 0.675,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.3480710983276367,
      "learning_rate": 0.0002904035476718404,
      "loss": 0.6695,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.35369980335235596,
      "learning_rate": 0.0002893436807095344,
      "loss": 0.6564,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.34858423471450806,
      "learning_rate": 0.0002882838137472284,
      "loss": 0.73,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.38727301359176636,
      "learning_rate": 0.0002872239467849224,
      "loss": 0.7226,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3514190912246704,
      "learning_rate": 0.0002861640798226164,
      "loss": 0.6677,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.32031717896461487,
      "learning_rate": 0.00028510421286031043,
      "loss": 0.6062,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.331730455160141,
      "learning_rate": 0.0002840443458980045,
      "loss": 0.7022,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.4256860017776489,
      "learning_rate": 0.00028298447893569846,
      "loss": 0.7097,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.3607518672943115,
      "learning_rate": 0.0002819246119733925,
      "loss": 0.6439,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.38123568892478943,
      "learning_rate": 0.00028086474501108643,
      "loss": 0.6646,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.39127808809280396,
      "learning_rate": 0.0002798048780487805,
      "loss": 0.6371,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.35686156153678894,
      "learning_rate": 0.0002787450110864745,
      "loss": 0.6323,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.3885669708251953,
      "learning_rate": 0.0002776851441241685,
      "loss": 0.6621,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.3873898983001709,
      "learning_rate": 0.00027662527716186254,
      "loss": 0.6126,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.34716036915779114,
      "learning_rate": 0.0002755654101995566,
      "loss": 0.6504,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.36037853360176086,
      "learning_rate": 0.0002745055432372505,
      "loss": 0.6205,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.39890480041503906,
      "learning_rate": 0.00027344567627494455,
      "loss": 0.6177,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.34560099244117737,
      "learning_rate": 0.0002723858093126386,
      "loss": 0.655,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.3721412718296051,
      "learning_rate": 0.0002713259423503326,
      "loss": 0.579,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.3824993968009949,
      "learning_rate": 0.0002702660753880266,
      "loss": 0.6161,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.36128249764442444,
      "learning_rate": 0.00026920620842572066,
      "loss": 0.6186,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.37080761790275574,
      "learning_rate": 0.00026814634146341465,
      "loss": 0.5994,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.36798450350761414,
      "learning_rate": 0.00026708647450110864,
      "loss": 0.6322,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.36768820881843567,
      "learning_rate": 0.0002660266075388027,
      "loss": 0.6063,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.3624456524848938,
      "learning_rate": 0.00026496674057649666,
      "loss": 0.6349,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.36303475499153137,
      "learning_rate": 0.0002639068736141907,
      "loss": 0.6556,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.35183194279670715,
      "learning_rate": 0.00026284700665188474,
      "loss": 0.7064,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.3993893563747406,
      "learning_rate": 0.00026178713968957873,
      "loss": 0.5619,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.3761635720729828,
      "learning_rate": 0.0002607272727272727,
      "loss": 0.7157,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.3518609404563904,
      "learning_rate": 0.00025966740576496676,
      "loss": 0.6161,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.3438890278339386,
      "learning_rate": 0.00025860753880266074,
      "loss": 0.6724,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.3328075110912323,
      "learning_rate": 0.0002575476718403548,
      "loss": 0.6096,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.341993123292923,
      "learning_rate": 0.0002564878048780488,
      "loss": 0.6623,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.3386165499687195,
      "learning_rate": 0.0002554279379157428,
      "loss": 0.6903,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.3305959105491638,
      "learning_rate": 0.0002543680709534368,
      "loss": 0.6211,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.39799752831459045,
      "learning_rate": 0.00025330820399113084,
      "loss": 0.6699,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.3469226658344269,
      "learning_rate": 0.0002522483370288248,
      "loss": 0.6463,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.3675510883331299,
      "learning_rate": 0.00025118847006651887,
      "loss": 0.6359,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.3591601550579071,
      "learning_rate": 0.0002501286031042129,
      "loss": 0.6551,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.3752742409706116,
      "learning_rate": 0.0002490687361419069,
      "loss": 0.6363,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.3341800272464752,
      "learning_rate": 0.0002480088691796009,
      "loss": 0.6555,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.31694409251213074,
      "learning_rate": 0.0002469490022172949,
      "loss": 0.6805,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.3443235754966736,
      "learning_rate": 0.0002458891352549889,
      "loss": 0.7189,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.34567585587501526,
      "learning_rate": 0.00024482926829268295,
      "loss": 0.6488,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.36196082830429077,
      "learning_rate": 0.00024376940133037696,
      "loss": 0.6359,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.3510529398918152,
      "learning_rate": 0.00024270953436807097,
      "loss": 0.6723,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4168505370616913,
      "learning_rate": 0.00024164966740576496,
      "loss": 0.7087,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.38020339608192444,
      "learning_rate": 0.00024058980044345897,
      "loss": 0.5715,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.38518226146698,
      "learning_rate": 0.000239529933481153,
      "loss": 0.6339,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.3704150915145874,
      "learning_rate": 0.00023847006651884703,
      "loss": 0.6312,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.40710920095443726,
      "learning_rate": 0.00023741019955654104,
      "loss": 0.618,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.3664563000202179,
      "learning_rate": 0.00023635033259423503,
      "loss": 0.7021,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.3638814687728882,
      "learning_rate": 0.00023529046563192907,
      "loss": 0.6463,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.3495710790157318,
      "learning_rate": 0.00023423059866962308,
      "loss": 0.6364,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.43735426664352417,
      "learning_rate": 0.00023317073170731707,
      "loss": 0.5803,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.3874286413192749,
      "learning_rate": 0.0002321108647450111,
      "loss": 0.6517,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.372635155916214,
      "learning_rate": 0.00023105099778270512,
      "loss": 0.5424,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.38414841890335083,
      "learning_rate": 0.0002299911308203991,
      "loss": 0.6287,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.35481685400009155,
      "learning_rate": 0.00022893126385809315,
      "loss": 0.5904,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.35485097765922546,
      "learning_rate": 0.00022787139689578716,
      "loss": 0.6502,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3545805513858795,
      "learning_rate": 0.00022681152993348115,
      "loss": 0.544,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.37257933616638184,
      "learning_rate": 0.00022575166297117516,
      "loss": 0.7303,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.3837604522705078,
      "learning_rate": 0.0002246917960088692,
      "loss": 0.6462,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.3463748097419739,
      "learning_rate": 0.0002236319290465632,
      "loss": 0.6288,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.39985474944114685,
      "learning_rate": 0.0002225720620842572,
      "loss": 0.6717,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.3414364159107208,
      "learning_rate": 0.00022151219512195125,
      "loss": 0.6287,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.3536858856678009,
      "learning_rate": 0.00022045232815964523,
      "loss": 0.6282,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.37838828563690186,
      "learning_rate": 0.00021939246119733925,
      "loss": 0.6821,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.3840574324131012,
      "learning_rate": 0.0002183325942350333,
      "loss": 0.6842,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.335237979888916,
      "learning_rate": 0.00021727272727272727,
      "loss": 0.6344,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.36624881625175476,
      "learning_rate": 0.0002162128603104213,
      "loss": 0.6333,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.3410489857196808,
      "learning_rate": 0.00021515299334811533,
      "loss": 0.6458,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.364812970161438,
      "learning_rate": 0.00021409312638580931,
      "loss": 0.6956,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.3746534585952759,
      "learning_rate": 0.00021303325942350333,
      "loss": 0.5852,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.40282800793647766,
      "learning_rate": 0.00021197339246119737,
      "loss": 0.6749,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.36745432019233704,
      "learning_rate": 0.00021091352549889135,
      "loss": 0.609,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.41321292519569397,
      "learning_rate": 0.00020985365853658537,
      "loss": 0.7046,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.38721373677253723,
      "learning_rate": 0.0002087937915742794,
      "loss": 0.6445,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.36334601044654846,
      "learning_rate": 0.0002077339246119734,
      "loss": 0.6591,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.386513352394104,
      "learning_rate": 0.0002066740576496674,
      "loss": 0.6432,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.34174248576164246,
      "learning_rate": 0.00020561419068736142,
      "loss": 0.6127,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.346197247505188,
      "learning_rate": 0.00020455432372505544,
      "loss": 0.6522,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.32458236813545227,
      "learning_rate": 0.00020349445676274945,
      "loss": 0.6118,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.3451327681541443,
      "learning_rate": 0.00020243458980044346,
      "loss": 0.6956,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.36170217394828796,
      "learning_rate": 0.00020137472283813748,
      "loss": 0.6422,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.3806750774383545,
      "learning_rate": 0.0002003148558758315,
      "loss": 0.652,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.32417619228363037,
      "learning_rate": 0.0001992549889135255,
      "loss": 0.5817,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.3380397856235504,
      "learning_rate": 0.00019819512195121952,
      "loss": 0.6243,
      "step": 270
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2362411570542387e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}